检索结果-内蒙古大学图书馆

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Deshpande, Sudhindra B. Velrani, K. Sundara Bhagyalakshmi, A. Vani, M. Sowmya Ananthi, S.N. Sahu, Devika Department of Information Science and Engineering KLS Gogte Institute of Technology Udyambag Karnataka Belagavi590006 India Department of Information Technology Sathyabama Institute of Science and Technology Tamil Nadu Chennai600119 India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu Chennai600062 India Department of Computer Application Mohan Babu University Andhra Pradesh Tirupati517501 India Department of Computer Science and Engineering S.A Engineering College Tamil Nadu Chennai600077 India Department of Computer Science and Engineering Government Engineering College Chhattisgarh Raipur492001 India

ISBN: (纸本)9798350374933

Artificial neural networks have made Natural Language Processing (NLP) a lot different because they can encode language data more efficiently. A lot of different natural language processing tasks, like mood analysis, translation, and text production, have been done very well with these networks are based on the neuronal structure of the human brain. This abstract delves into the fundamental principles of neural networks in natural language processing, with a particular emphasis on notable structures, including the more recent Transformer models, CNNs, and RNNs. The investigation investigates the potential future trajectories, challenges, and applications of improving language comprehension and developing assignments. © 2024 IEEE.

关键词： Natural language processing neural networks neural networks NLP recurrent neural networks RNNs

来源：评论

学校读者我要写书评

暂无评论

Distributed Machine Learning System for Intrusion Detection 2

Distributed Machine Learning System for Intrusion Detection

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Patil, Harshal Lohumi, Yogesh Tejaswini, K.M. Sudheendramouli, H.C. Parikh, Swapnil Maranan, Ramya Sri Balaji University Pune India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Sri Siddhartha Institute of Technology Department of Mathematics Tumakuru India Gsss Simha SubbaMahalakshmi First Grade College Department of Computer Science and Application Mysuru India Parul University Department of Computer Science and Engineering Parul Institute of Engineering and Technology Post Limda India Saveetha School of Engineering Simats Department of Research and Innovation Chennai India

ISBN: (纸本)9798350373110

As network systems expand in complexity, the necessity for effective intrusion detection grows. This study compares two distributed machine learning systems utilizing different communication topologies: Parameter Server and Point-to-Point. The former employs centralized parameter management for efficient communication, while the latter facilitates direct node-to-node communication without a central server. Using extensive network traffic data, the models are assessed on performance metrics like accuracy, scalability, and false positive rates. Both systems show promising results, with median accuracy and F1 scores around 93%. However, limitations include potential data homogeneity issues, scalability challenges particularly with the Parameter Server becoming a bottleneck, concerns over model overfitting, and high computational overhead in maintaining models across numerous nodes. Addressing these drawbacks is crucial for improving the reliability of intrusion detection systems in complex network environments. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Blockchain-IoT Layered Architecture, Current Trends, Challenges, and applications 7

Blockchain-IoT Layered Architecture, Current Trends, Challen...

引用

7th International Conference on Trends in Electronics and Informatics, ICOEI 2023

作者： Kumar, Mukesh Nidhi Tiwari, Shweta Kaur, Surinder School of Computer Application Lovely Professional University Phagwara India Maharaja Agrasen University Kallujhanda Himachal Pradesh Solan India Computer Science and Engineering Chandigarh University Punjab Mohali India

ISBN: (纸本)9798350397284

The term 'Internet of Things' (IoT) refers to the potential global connectivity of billions of individually networked devices that can collect and share data. This connectivity might occur everywhere on the globe. By combining IoT with Blockchain (BC), a robust and secure system might be created to store information gathered by intelligent gadgets. Internet-connected IoT devices can upload transaction data to private BC networks. As a result, all transactions in such networks are recorded in immutable ledgers. In order to comprehend how devices may connect with one another, this study examines the interplay between BC technology and IoTs. In this article, a BC layered architecture as a practical framework for integrating BC technology with IoT by making use of state-of-the-art tools and methods is proposed. Current trends and difficulties, as well as potential application domains, are discussed which is in relation to the layered architecture of Blockchain technology. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Utilizing Random Forests for High-Accuracy Classification in Medical Diagnostics 7

Utilizing Random Forests for High-Accuracy Classification in...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Maindola, Meenakshi Al-Fatlawy, Ramy Riad Kumar, Rakesh Boob, Nandini Shirish Sreeja, S.P. Sirisha, N. Srivastava, Abhinav Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun India The Islamic university College of technical engineering Department of computers Techniques engineering Najaf Iraq Gla University Department of Computer Engineering & Applications Mathura India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Tamilnadu Chennai India New Horizon College of Engineering Master of Computer Application Bangalore India Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India Fs University Shikohabad Firozabad India

ISBN: (纸本)9798350350067

In recent years, medical diagnostics has increasingly relied on machine learning techniques to improve accuracy and efficiency. Among these, the Random Forest algorithm has emerged as a powerful tool for classification tasks due to its robustness and ability to handle complex datasets. This paper explores the application of Random Forests in medical diagnostics, specifically focusing on enhancing the accuracy of disease classification. By analyzing large, heterogeneous medical datasets, we demonstrate how Random Forests can outperform traditional classification algorithms, offering high precision in identifying and classifying diseases. Key features, such as decision tree ensemble methods and bootstrap aggregation, are utilized to minimize overfitting and improve model generalization. The research compares Random Forests to other machine learning models, such as Neural Networks and Support Vector Machines, and finds that Random Forests perform better in terms of dependability and classification accuracy. We further emphasise that the technique can scale to big datasets and that it can manage missing data. The findings show that Random Forests might be a useful tool for accurate and early diagnosis when incorporated into clinical procedures. The findings of this study highlight the promise of machine learning, and Random Forests in particular, to revolutionise healthcare diagnostics and enhance patient results. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

A human-in-the-loop method for pulmonary nodule detection in CT scans

引用

Visual Intelligence 2024年第1期2卷 1-13页

作者： Zeng, Qingjie Xie, Yutong Lu, Zilin Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an 710072 China Australian Institute for Machine Learning The University of Adelaide Adelaide 5000 SA Australia

Automated pulmonary nodule detection using computed tomography scans is vital in the early diagnosis of lung cancer. Although extensive well-performed methods have been proposed for this task, they suffer from the domain shift issue between training and test images. Unsupervised domain adaptation (UDA) methods provide a promising means to mitigate the domain variance;however, their performance is still limited since no target domain supervision is introduced. To make the pulmonary nodule detection algorithm more applicable in clinical practice and further boost the performance across domains, we propose a human-in-the-loop method in a semi-supervised fashion to enhance the model generalization ability when transferred from source domain to target domain. Specifically, we first train a detector model on source domain, and then the pre-trained detector is utilized with our proposed uncertainty-guided sample selection scheme (USSS) to find a few target domain samples worth annotating most and obtain their human annotations. Finally, the annotated and the rest unlabeled target domain samples are used together to refine the pre-trained model via our proposed zoom-in and zoom-out constraint (ZZC) strategy. We evaluate our method on the Nodule Analysis 2016 (LUNA16) and TianChi datasets. Experimental results show that our method surpasses recent competitive methods on source domain and also achieves surprising performance on target domain. © The Author(s) 2024.

关键词： Domain adaptation Human-in-the-loop Pulmonary nodule detection Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Supervised and Unsupervised Coupled Generative Adversarial Networks in Multivariate Time Series 4

Supervised and Unsupervised Coupled Generative Adversarial N...

引用

4th International Conference on Information science, Parallel and Distributed Systems, ISPDS 2023

作者： Wang, Qinfen Li, Yifei Xia, Yong School of Computer Science and Engineering Northwestern Polytechnical University Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an710072 China

ISBN: (纸本)9798350337181

Generative adversarial networks (GAN) have been successful in demonstrating the efficiency of generative time series. In this paper, we proposed a novel end-to-end supervised and unsupervised coupled generative adversarial networks (SUC-GAN) framework that consists of a gated recurrent unit (GRU) for generating multivariate time series. We test SUC-GAN on three datasets (i.e. Sines, Energy, Stocks) to investigate the efficacy and properties. The preliminary results show the potential power of supervised, unsupervised, and coupled learning for data generation. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Industrial IoT Smart Manufacturing Systems based on Cloud Computing Energy Efficiency Analysis using Machine Learning Algorithms 3

Industrial IoT Smart Manufacturing Systems based on Cloud Co...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Chinnasamy, P. Khan, Patan Feridoz Sasikala, C. Swathi, Mavalluru Kumar, M. Prema Yadav, Ajay Kumar Kalasalingam Academy of Research and Education School of Computing Department of Computer Science and Engineering Tamilnadu India Mohan Babu University School of Computing Department of Computer Science and Engineering Andhra Pradesh Tirupati India Dept of Cse Andhra Pradesh Ananthapuramu India Audisankara College of Engineering and Technology Andhra Pradesh India Dept. of Ece Andhra Pradesh Bhimavaram India United Institute of Management Department of Computer Application Prayagraj India

ISBN: (纸本)9798331509675

With open connectivity and emergent computing, the Industrial Internet of Things (IIoT) combined with cloud computing resources provides significant breakthroughs in the field of industrial automation. These developments lead to the evolution of supplemental services, which improve automation in the production and industrial sectors. This research proposes novel technique in smart manufacturing system based on cloud computing with IIoT in energy efficiency using machine learning. Here the smart manufacturing process has been analysed based on IIoT with cloud computing network, where the energy efficiency is analysed using virtual machine-based reinforcement markov chain based linear regression. Experimental analysis has been carried out in terms of latency, energy efficiency, task response time, accuracy. proposed technique obtained 97% of Latency, 95% of Energy efficiency, 98% of Accuracy, 94% of Task response time. © 2025 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Optimization of Software Quality Model Using Improvised Genetic Algorithm and EEM 1

Hyperparameter Optimization of Software Quality Model Using ...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Singh, Rakhi Sharma, Vishnu Kaushik, Neeraj Malhotra, Ritu Rauthan, Hemlata Delhi Institute of Higher Education Department of Computer Application Greater Noida India ITS Engineering College Department Of Computer Science and Engineering Greater Noida India Galgotias College of Engineering and Tehnology Department of Computer Applications Greater Noida India GNIOT Institute of Professional Studies Department of Computer Applications Greater Noida India Delhi Institute of Higher Education Department of Computer Applications Greater Noida India

ISBN: (纸本)9798350356816

Software quality analysis has become one of the topmost concerns in the modern world and requires the massive attention of developers and testers during software development. Software quality analysis is a multidimensional notion and one attribute may not describe the software product's overall quality. Software developer's objective is to build a software product that attains the highest quality which depends on multifarious attributes namely functional suitability, maintainability, etc. However, analysis of software product quality is challenging in both the development and maintenance phases. This research is aimed at hyperparameter optimization of the software quality model using an improvised genetic algorithm and an enhanced ensemble model (EEM) approach. In this research, there has been shown the optimal possibility of software quality model hyperparameter optimization using the modified architecture of genetic algorithm along with EEM. To validate the performance of this suggested approach, PROMISE Repository datasets have been utilized. As a result, this proposed approach achieves all performance metrics very optimal. The evaluated values of accuracy, precision, recall, and F1- score are 99.45%, 98.83%, 97.28%, and 99.37%, respectively. In the future, this approach may be integrated with modified architectures of software quality models for automated software product quality analysis. © 2024 IEEE.

关键词： Software quality

来源：评论

学校读者我要写书评

暂无评论

Effective Intrusion Detection Model Using Raptor Optimized Deep Convolutional Neural Network

Effective Intrusion Detection Model Using Raptor Optimized D...

引用

2023 IEEE Guwahati Subsection Conference, GCON 2023

作者： Mahanta, Kshyamasagar Maringanti, Hima Bindu Bhale, Pradeepkumar Maharaja Sriram Chandra Bhanja Deo University Department of Computer Application Odisha Mayurbhanj757003 India Indian Institute of Technology Department of Computer Science and Engineering Guwahati Guwahati781039 India

ISBN: (纸本)9798350337785

Malicious behavior in the system must be recognized for ensure security because the occurrence of the intrusions can threaten the valuable data and threatens the quality of the network. An important area of research in network security is network intrusion detection. In recent years the intrusion detection model faced several problems due to low accuracy, data imbalance, lack of optimization and so on. To overcome this issue, in this research, a raptor-optimized deep CNN is used to develop the intrusion detection model, where the occurrence of intrusions is effectively detected. The deep CNN classifier effectively learns the features, and the enabling of the raptor optimization optimizes the weights and bias parameters to enhance the performance of the deep CNN classifier. The raptor optimization improves the classifier convergence time and global search capability, and the enabling of Synthetic Minority Oversampling Technique (SMOTE) resolved the issues of data imbalance, which reduced the complexity of the system. By evaluating the parameters of accuracy, sensitivity, and specificity, the research's superiority is demonstrated, and the suggested raptor-optimized deep CNN classifier achieved values of 96.51%, 90.23%, and 97.71% for dataset 1. The proposed raptor optimization also achieved values of 95.39%, 95.83%, and 95.15% for dataset 2, which is highly efficient compared to other existing methods. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Driven X-ray Classification for Pneumonia Detection Using CNN

Deep Learning Driven X-ray Classification for Pneumonia Dete...

引用

Communication, Control and Intelligent Systems (CCIS)

作者： Sarvagya Saxena Siddhartha Khandelwal Sneha Chaudhary Priyanka Gupta Computer Science Engineering GLA University Vrindavan India Computer Science Engineering GLA University Mathura India Computer Engineering & Application GLA University Mathura India

ISBN: (数字)9798331528201

ISBN: (纸本)9798331528218

Major deaths (55% or 1.5 million) of LRI (Lower Respiratory Infections) are caused due to Pneumococcal pneumonia. LRI is the 5th highest cause of demise as mentioned by the Global Burden of Disease Study 2015. Health organization suffers from a lack of Physicians. A Physician handles so many cases which leads to misdiagnoses. To resolve all these issues we came up with an easy-to-handle, and implemented in health organizations, the CNN model. The main aim of this model is to help the healthcare professionals by providing them with a tool which will help them detect Pneumococcal pneumonia. With the help of this tool, the work strain of a doctor can be reduced. This model is developed without any pre-trained model and for better accuracy, an immense dataset is used. All the X-ray images were pre processed before being introduced to the neural network. Different layers have been used to make the model more precise and make it adaptable for X-ray images under different conditions. The aim is to combine deep learning concepts with healthcare to make a positive and meaningful impact in the healthcare industry.

关键词： Deep learning Adaptation models Pneumonia Accuracy Computational modeling Neural networks Medical services Organizations X-ray imaging Strain

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：